Gemini 3.5 Flash vs Kimi K2 Thinking
Google vs Moonshot AI — benchmarks, pricing, and capabilities side by side.
- •Gemini 3.5 Flash has the higher intelligence index (92.2 vs 85.6)
- •Kimi K2 Thinking is cheaper ($0.60 vs $1.50 per 1M input)
- •Gemini 3.5 Flash is faster
- •Gemini 3.5 Flash has a larger context window (1M)
| Gemini 3.5 Flash | Kimi K2 Thinking | |
|---|---|---|
| Intelligence index | 92.2 | 85.6 |
| Developer | Moonshot AI | |
| Type | Multimodal | LLM |
| Access | API only | Open weights |
| Context window | 1,048,576 tokens | 262,144 tokens |
| Input price | $1.50 / 1M | $0.60 / 1M |
| Output price | $9.00 / 1M | $2.50 / 1M |
| Speed | 221 tok/s | 100 tok/s |
| Released | May 19, 2026 | November 6, 2025 |
| Parameters | — | 1T (32B active) |
| Input modalities | Text, Image, Audio, Video | Text |
| Output modalities | Text | Text |
Shared benchmarks
Gemini 3.5 Flash
Kimi K2 Thinking
GPQA Diamond
92.2
84.5
Humanity’s Last Exam
41
22.3